Combining Pattern Classifiers: Methods and Algorithms

@inproceedings{Kuncheva2004CombiningPC,
  title={Combining Pattern Classifiers: Methods and Algorithms},
  author={Ludmila I. Kuncheva},
  year={2004}
}
Thank you for downloading combining pattern classifiers methods and algorithms. Maybe you have knowledge that, people have look hundreds times for their chosen novels like this combining pattern classifiers methods and algorithms, but end up in infectious downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they cope with some harmful virus inside their computer. 
Cascading an Emerging Pattern Based Classifier
TLDR
A novel algorithm to find emerging patterns without global discretization is introduced and a new method for building cascades of emerging pattern classifiers is proposed, which combines the higher accuracy of classifying with higher support thresholds with the lower levels of abstention of classify with lower thresholds.
Dynamic Classifier Systems and Their Applications to Random Forest Ensembles
TLDR
This paper provides a general framework for dynamic classifier systems, which use dynamic confidence measures to adapt to a particular pattern, and experiments with random forests show that dynamic classifiers systems can significantly outperform both confidence-free and staticclassifier systems.
A New Emerging Pattern Mining Algorithm and Its Application in Supervised Classification
TLDR
A novel algorithm to find emerging patterns without global discretization, which uses an accurate estimation of the support threshold, and attains higher accuracy than other understandable classifiers, while being competitive with Nearest Neighbors and Support Vector Machines classifiers.
A Learning Algorithm for the Optimum-Path Forest Classifier
TLDR
A learning algorithm is introduced for the OPF-based classifiers and it is shown that a classifier can learns with its own errors without increasing its training set.
A Team Is Superior to an Individual
This chapter deals with connecting classifiers into a team. It explains the concepts of aggregation function and confidence, the difference between general teams and ensembles and main methods of
Information theoretic combination of pattern classifiers
TLDR
An information theoretic score (ITS) that expresses a trade-off between individual accuracy and diversity is proposed, showing that the selection based on the ITS outperforms state-of-the-art diversity-based selection techniques.
Use of Structured Pattern Representations for Combining Classifiers
TLDR
Combination of classifiers has been applied using tree pattern representation in combination with strings and vectors for a handwritten character classification task in order to save computational cost.
Ensemble of Classifiers with Modification of Confidence Values
TLDR
The algorithm which modifies the confidence values of the ensemble of classifiers is proposed and results show that the proposed method is a promising method for the development of multiple classifiers systems.
A Model-Based Approach for Building Optimum Classification Cascades
TLDR
In this chapter, a model-based algorithm of automatic generation of optimum classification cascades is devised and given a large pool of classifiers, it builds a cascade that achieves the lowest possible recognition time while preserving the accuracy of the most powerful classifier in the pool.
A survey of emerging patterns for supervised classification
TLDR
The state-of-the-art methods for mining emerging patterns are reviewed, classify them by different taxonomies, and identify new trends to help researchers and users to select the appropriate algorithm for a given application.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 297 REFERENCES
Experiments with Classifier Combining Rules
TLDR
It is shown that there is no overall winning combining rule and that bad classifiers as well as bad feature sets may contain valuable information for performance improvement by combining rules.
Clustering-and-selection model for classifier combination
  • L. Kuncheva
  • Computer Science
    KES'2000. Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Proceedings (Cat. No.00TH8516)
  • 2000
TLDR
A simple clustering-and-selection algorithm based on a probabilistic interpretation of classifier selection, where the most successful classifier for a given cluster is nominated to label the inputs in the Voronoi cell of the cluster centroid.
Optimal combinations of pattern classifiers
  • L. Lam, C. Suen
  • Mathematics, Computer Science
    Pattern Recognit. Lett.
  • 1995
TLDR
A Bayesian formulation and a weighted majority vote (with weights obtained through a genetic algorithm) are implemented, and the combined performances of 7 classifiers on a large set of handwritten numerals are analyzed.
On Combining Classifiers
We develop a common theoretical framework for combining classifiers which use distinct pattern representations and show that many existing schemes can be considered as special cases of compound
Data Dependence in Combining Classifiers
TLDR
A new categorization of combining schemes based on their dependence on the data patterns being classified is presented, arguing that data dependent, and especially explicitly datadependent, approaches represent the highest potential for improved performance.
Decision Combination in Multiple Classifier Systems
TLDR
This work proposes three methods based on the highest rank, the Borda count, and logistic regression for class set reranking that have been tested in applications of degraded machine-printed characters and works from large lexicons, resulting in substantial improvement in overall correctness.
Combination of Multiple Classifiers Using Local Accuracy Estimates
TLDR
A method for combining classifiers that uses estimates of each individual classifier's local accuracy in small regions of feature space surrounding an unknown test sample to confirm the validity of this approach.
Neural and statistical classifiers-taxonomy and two case studies
TLDR
This work gives a tutorial overview in which popular classifiers are grouped into distinct categories according to their underlying mathematical principles; also, what makes a classifier neural is assessed.
A multinomial selection procedure for evaluating pattern recognition algorithms
TLDR
This new application of MSP demonstrates increased differentiation power over traditional classifier evaluation methods when applied to three “toy” problems of varying difficulty.
A note on comparing classifiers
  • R. Duin
  • Computer Science
    Pattern Recognit. Lett.
  • 1996
TLDR
It is argued that a straightforward fair comparison demands automatic classifiers with no user interaction, as this conflicts with one of the main characteristics of neural networks, their flexibility, the question whether they are better or worse than traditional techniques might be undecidable.
...
1
2
3
4
5
...